© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97510
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     крайней
    -0.56
    ржа
    -0.49
    DialogTitle
    -0.48
     Städten
    -0.44
     çıkar
    -0.43
     AssemblyCompany
    -0.43
     JFrame
    -0.42
    HORE
    -0.41
     esclu
    -0.41
    visel
    -0.41
    POSITIVE LOGITS
    writeFieldEnd
    0.95
    matchCondition
    0.73
     تضيفلها
    0.71
    ❹
    0.69
    MessageTagHelper
    0.66
    UrlResolution
    0.65
    AccessorTable
    0.63
    béco
    0.63
    WebElementEntity
    0.63
     صوتيه
    0.63
    Activations Density 1.578%

    No Known Activations